An MCP server for setting spending limits and keeping audit trails when AI agents pay for things. An audit trail is a record of actions and transactions that can be reviewed later.

Use it to control agent payments with programmable limits and review records of spending.

It is intended to limit what an agent can spend and make its payments traceable.

imprest — MCP server by Theoddalex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/Theoddalex/imprest

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/theoddalex/imprest/imprest/github.svg)](https://agentmods.dev/mcp/theoddalex/imprest/imprest)

Your own site

<a href="https://agentmods.dev/mcp/theoddalex/imprest/imprest"><img src="https://agentmods.dev/badge/mcp/theoddalex/imprest/imprest/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/theoddalex/imprest/imprest"><img src="https://agentmods.dev/badge/mcp/theoddalex/imprest/imprest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

imprest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

listed in the official MCP registry · 8 lines

What it actually says

{ "imprest": { "command": "uvx", "args": [ "imprest" ] } }

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 8 lines scan A 7b35be101e3a

Subscribe to this mod's changes

imprest is an MCP server published in the GitHub repository Theoddalex/imprest (0 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Finance and fintech Guardrails Security agent-payments ai-agents ethereum mcp mcp-server

verantis-mcp

MCP server for Verantis — the verified directory for machine payments (x402 & MPP). Find live-verified services and check a wallet before your agent pays. Runs locally from the verantis-mcp Python package. Needs 1 environment variable to run.

m9labs-railscope/verantis-mcp · not measured

frisk

Screen the counterparty of an x402 payment before an agent pays it. Runs offline by default. Runs locally from the frisk-mcp npm package. Needs 2 environment variables to run.

Jiangw2718i/frisk · not measured

canton-agent-mcp

MCP server that lets AI agents pay on the Canton Network through a human's mobile wallet: the agent asks, the human approves on their phone, hardware signs. Runs locally from the canton-agent-mcp npm package.

vsima/canton-agent-mcp · not measured

hpp-x402

MCP stdio bridge that lets Claude Desktop / OpenClaw / other MCP hosts make x402 payments on HPP — autoTopup from a Safe via AllowanceModule, signs EIP-3009 with a delegate EOA. Runs locally from the @hpp-io/x402-mcp-bridge npm package. Needs 8 environment variables to run.

hpp-io/x402-mcp-bridge · not measured

x402-mcp-bridge

MCP bridge for autonomous x402 payments in HPP USDC.e — discover and pay for services per call. Runs locally from the @hpp-io/x402-mcp-bridge npm package. Needs 5 environment variables to run.